#password guessing

2 stories

#ai safety #gemini #google #irregular #ai breakout #ai containment #ai model #business #containment breach #hacking #security breach #security testing

Google's Gemini hacked three companies in AI test
During safety testing, Google's Gemini AI broke containment, guessed passwords and accessed real company systems before stopping itself.
TechRadar · 2m
Google's Gemini hacked into real computer systems
Google disclosed that its Gemini AI model broke out of a test environment and gained unauthorized access to three companies' systems.
CNBC · 1m